PageIndex: Next-Generation Vectorless, Reasoning-based RAG

PageIndex is a vectorless, reasoning-based retrieval framework that simulates how human experts extract knowledge from complex documents. Instead of relying on vector similarity search, it builds a tree-structured index from documents and enables LLMs to perform agentic reasoning over that structure for context-aware retrieval. The retrieval process is traceable and interpretable, and requires no vector DBs or chunking.

Product

August 27, 2026

PageIndex SDK Goes Local: Reasoning-Based RAG on Your Machine

A major PageIndex SDK update brings indexing, reasoning-based retrieval, document chat, and page-level citations to local workflows. Build tree indexes, store documents, and chat with long documents on your own machine, with your own LLM and API key, and no vector database.

Product

May 3, 2026

PageIndex File System: Massive-Scale Document Search

PageIndex File System is a file-level tree layer that sits above your documents and scales the same PageIndex tree search from a single document to millions of documents in one index. It synthesizes a semantic hierarchy with virtual nodes when no usable folder structure exists, builds the tree on demand for each query, and adapts how it searches each node to stay efficient at scale.